Fix crewai-tools version

docs/concepts/knowledge.mdx

@@ -48,6 +48,7 @@ from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSourc
 content = "Users name is John. He is 30 years old and lives in San Francisco."
 string_source = StringKnowledgeSource(
     content=content, 
+    metadata={"preference": "personal"}
 )
 
 # Create an LLM with a temperature of 0 to ensure deterministic outputs
@@ -73,7 +74,10 @@ crew = Crew(
     tasks=[task],
     verbose=True,
     process=Process.sequential,
-    knowledge_sources=[string_source], # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
+    knowledge={
+      "sources": [string_source], 
+      "metadata": {"preference": "personal"}
+    }, # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
 )
 
 result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
@@ -81,6 +85,17 @@ result = crew.kickoff(inputs={"question": "What city does John live in and how o
 
 ## Knowledge Configuration
 
+### Metadata and Filtering
+
+Knowledge sources support metadata for better organization and filtering. Metadata is used to filter the knowledge sources when querying the knowledge store.
+
+```python Code
+knowledge_source = StringKnowledgeSource(
+    content="Users name is John. He is 30 years old and lives in San Francisco.",
+    metadata={"preference": "personal"} # Metadata is used to filter the knowledge sources
+)
+```
+
 ### Chunking Configuration
 
 Control how content is split for processing by setting the chunk size and overlap.
@@ -101,28 +116,21 @@ You can also configure the embedder for the knowledge store. This is useful if y
 ...
 string_source = StringKnowledgeSource(
     content="Users name is John. He is 30 years old and lives in San Francisco.",
+    metadata={"preference": "personal"}
 )
 crew = Crew(
     ...
-    knowledge_sources=[string_source],
-    embedder={
-        "provider": "openai",
-        "config": {"model": "text-embedding-3-small"},
+    knowledge={
+        "sources": [string_source],
+        "metadata": {"preference": "personal"},
+        "embedder_config": {
+          "provider": "openai", # Default embedder provider; can be "ollama", "gemini", e.t.c.
+          "config": {"model": "text-embedding-3-small"} # Default embedder model; can be "mxbai-embed-large", "nomic-embed-tex", e.t.c.
+        },
     },
 )
 ```
 
-## Clearing Knowledge
-
-If you need to clear the knowledge stored in CrewAI, you can use the `crewai reset-memories` command with the `--knowledge` option.
-
-```bash Command
-crewai reset-memories --knowledge
-```
-
-This is useful when you've updated your knowledge sources and want to ensure that the agents are using the most recent information.
-
-
 ## Custom Knowledge Sources
 
 CrewAI allows you to create custom knowledge sources for any type of data by extending the `BaseKnowledgeSource` class. Let's create a practical example that fetches and processes space news articles.
@@ -166,12 +174,12 @@ class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
         formatted = "Space News Articles:\n\n"
         for article in articles:
             formatted += f"""
-                Title: {article['title']}
-                Published: {article['published_at']}
-                Summary: {article['summary']}
-                News Site: {article['news_site']}
-                URL: {article['url']}
-                -------------------"""
+Title: {article['title']}
+Published: {article['published_at']}
+Summary: {article['summary']}
+News Site: {article['news_site']}
+URL: {article['url']}
+-------------------"""
         return formatted
 
     def add(self) -> None:
@@ -181,12 +189,17 @@ class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
             chunks = self._chunk_text(text)
             self.chunks.extend(chunks)
         
-        self._save_documents()
+        self.save_documents(metadata={
+            "source": "space_news_api",
+            "timestamp": datetime.now().isoformat(),
+            "article_count": self.limit
+        })
 
 # Create knowledge source
 recent_news = SpaceNewsKnowledgeSource(
     api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
     limit=10,
+    metadata={"category": "recent_news", "source": "spaceflight_news"}
 )
 
 # Create specialized agent
@@ -252,7 +265,7 @@ The latest developments in space exploration, based on recent space news article
    - Implements three key methods:
      - `load_content()`: Fetches articles from the API
      - `_format_articles()`: Structures the articles into readable text
-     - `add()`: Processes and stores the content
+     - `add()`: Processes and stores the content with metadata
 
 2. **Agent Configuration**:
    - Specialized role as a Space News Analyst
@@ -286,12 +299,14 @@ You can customize the API query by modifying the endpoint URL:
 recent_news = SpaceNewsKnowledgeSource(
     api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
     limit=20,  # Increase the number of articles
+    metadata={"category": "recent_news"}
 )
 
 # Add search parameters
 recent_news = SpaceNewsKnowledgeSource(
     api_endpoint="https://api.spaceflightnewsapi.net/v4/articles?search=NASA", # Search for NASA news
     limit=10,
+    metadata={"category": "nasa_news"}
 )
 ```
 
@@ -299,14 +314,16 @@ recent_news = SpaceNewsKnowledgeSource(
 
 <AccordionGroup>
   <Accordion title="Content Organization">
+    - Use descriptive metadata for better filtering
     - Keep chunk sizes appropriate for your content type
     - Consider content overlap for context preservation
     - Organize related information into separate knowledge sources
   </Accordion>
   
   <Accordion title="Performance Tips">
+    - Use metadata filtering to narrow search scope
     - Adjust chunk sizes based on content complexity
     - Configure appropriate embedding models
     - Consider using local embedding providers for faster processing
   </Accordion>
-</AccordionGroup>
+</AccordionGroup>

docs/how-to/agentops-observability.mdx

@@ -57,7 +57,7 @@ This feature is useful for debugging and understanding how agents interact with
    <Step title="Install AgentOps">
       Install AgentOps with:
       ```bash
-      pip install 'crewai[agentops]'
+      pip install crewai[agentops]
       ```
       or
       ```bash

pyproject.toml

@@ -64,7 +64,7 @@ dev-dependencies = [
     "mkdocs-material-extensions>=1.3.1",
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
-    "crewai-tools>=0.14.0",
+    "crewai-tools>=0.17.0,<0.18.0",
     "pytest>=8.0.0",
     "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",

src/crewai/cli/templates/crew/config/tasks.yaml

@@ -12,6 +12,6 @@ reporting_task:
     Review the context you got and expand each topic into a full section for a report.
     Make sure the report is detailed and contains any and all relevant information.
   expected_output: >
-    A fully fledged report with the main topics, each with a full section of information.
+    A fully fledge reports with the mains topics, each with a full section of information.
     Formatted as markdown without '```'
   agent: reporting_analyst

src/crewai/knowledge/knowledge.py

@@ -1,10 +1,11 @@
 import os
-from typing import Any, Dict, List, Optional
 
+from typing import List, Optional, Dict, Any
 from pydantic import BaseModel, ConfigDict, Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+from crewai.utilities.constants import DEFAULT_SCORE_THRESHOLD
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"  # removes logging from fastembed
 
@@ -45,7 +46,9 @@ class Knowledge(BaseModel):
             source.storage = self.storage
             source.add()
 
-    def query(self, query: List[str], limit: int = 3) -> List[Dict[str, Any]]:
+    def query(
+        self, query: List[str], limit: int = 3, preference: Optional[str] = None
+    ) -> List[Dict[str, Any]]:
         """
         Query across all knowledge sources to find the most relevant information.
         Returns the top_k most relevant chunks.
@@ -54,6 +57,8 @@ class Knowledge(BaseModel):
         results = self.storage.search(
             query,
             limit,
+            filter={"preference": preference} if preference else None,
+            score_threshold=DEFAULT_SCORE_THRESHOLD,
         )
         return results
 

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -1,13 +1,13 @@
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Dict, List, Union
+from typing import Union, List, Dict, Any
 
 from pydantic import Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from crewai.utilities.logger import Logger
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
-from crewai.utilities.logger import Logger
 
 
 class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
@@ -49,9 +49,10 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
                     color="red",
                 )
 
-    def _save_documents(self):
+    def save_documents(self, metadata: Dict[str, Any]):
         """Save the documents to the storage."""
-        self.storage.save(self.chunks)
+        chunk_metadatas = [metadata.copy() for _ in self.chunks]
+        self.storage.save(self.chunks, chunk_metadatas)
 
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""

src/crewai/knowledge/source/base_knowledge_source.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional
+from typing import List, Dict, Any, Optional
 
 import numpy as np
 from pydantic import BaseModel, ConfigDict, Field
@@ -17,7 +17,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
     storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
-    metadata: Dict[str, Any] = Field(default_factory=dict)  # Currently unused
+    metadata: Dict[str, Any] = Field(default_factory=dict)
     collection_name: Optional[str] = Field(default=None)
 
     @abstractmethod
@@ -41,9 +41,9 @@ class BaseKnowledgeSource(BaseModel, ABC):
             for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
         ]
 
-    def _save_documents(self):
+    def save_documents(self, metadata: Dict[str, Any]):
         """
         Save the documents to the storage.
         This method should be called after the chunks and embeddings are generated.
         """
-        self.storage.save(self.chunks)
+        self.storage.save(self.chunks, metadata)

src/crewai/knowledge/source/csv_knowledge_source.py

@@ -1,6 +1,6 @@
 import csv
-from pathlib import Path
 from typing import Dict, List
+from pathlib import Path
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -30,7 +30,7 @@ class CSVKnowledgeSource(BaseFileKnowledgeSource):
         )
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self._save_documents()
+        self.save_documents(metadata=self.metadata)
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/excel_knowledge_source.py

@@ -1,6 +1,5 @@
-from pathlib import Path
 from typing import Dict, List
-
+from pathlib import Path
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
 
@@ -45,7 +44,7 @@ class ExcelKnowledgeSource(BaseFileKnowledgeSource):
 
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self._save_documents()
+        self.save_documents(metadata=self.metadata)
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/json_knowledge_source.py

@@ -1,6 +1,6 @@
 import json
-from pathlib import Path
 from typing import Any, Dict, List
+from pathlib import Path
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -42,7 +42,7 @@ class JSONKnowledgeSource(BaseFileKnowledgeSource):
         )
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self._save_documents()
+        self.save_documents(metadata=self.metadata)
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/pdf_knowledge_source.py

@@ -1,5 +1,5 @@
+from typing import List, Dict
 from pathlib import Path
-from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -43,7 +43,7 @@ class PDFKnowledgeSource(BaseFileKnowledgeSource):
         for _, text in self.content.items():
             new_chunks = self._chunk_text(text)
             self.chunks.extend(new_chunks)
-        self._save_documents()
+        self.save_documents(metadata=self.metadata)
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/string_knowledge_source.py

@@ -24,7 +24,7 @@ class StringKnowledgeSource(BaseKnowledgeSource):
         """Add string content to the knowledge source, chunk it, compute embeddings, and save them."""
         new_chunks = self._chunk_text(self.content)
         self.chunks.extend(new_chunks)
-        self._save_documents()
+        self.save_documents(metadata=self.metadata)
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/text_file_knowledge_source.py

@@ -1,5 +1,5 @@
-from pathlib import Path
 from typing import Dict, List
+from pathlib import Path
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -24,7 +24,7 @@ class TextFileKnowledgeSource(BaseFileKnowledgeSource):
         for _, text in self.content.items():
             new_chunks = self._chunk_text(text)
             self.chunks.extend(new_chunks)
-        self._save_documents()
+        self.save_documents(metadata=self.metadata)
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/storage/knowledge_storage.py

@@ -1,20 +1,18 @@
 import contextlib
-import hashlib
 import io
 import logging
-import os
-from typing import Any, Dict, List, Optional, Union, cast
-
 import chromadb
-import chromadb.errors
-from chromadb.api import ClientAPI
-from chromadb.api.types import OneOrMany
-from chromadb.config import Settings
+import os
 
-from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
-from crewai.utilities import EmbeddingConfigurator
-from crewai.utilities.logger import Logger
+import chromadb.errors
 from crewai.utilities.paths import db_storage_path
+from typing import Optional, List, Dict, Any, Union
+from crewai.utilities import EmbeddingConfigurator
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+import hashlib
+from chromadb.config import Settings
+from chromadb.api import ClientAPI
+from crewai.utilities.logger import Logger
 
 
 @contextlib.contextmanager
@@ -118,16 +116,11 @@ class KnowledgeStorage(BaseKnowledgeStorage):
     def save(
         self,
         documents: List[str],
-        metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
+        metadata: Union[Dict[str, Any], List[Dict[str, Any]]],
     ):
         if self.collection:
             try:
-                if metadata is None:
-                    metadatas: Optional[OneOrMany[chromadb.Metadata]] = None
-                elif isinstance(metadata, list):
-                    metadatas = [cast(chromadb.Metadata, m) for m in metadata]
-                else:
-                    metadatas = cast(chromadb.Metadata, metadata)
+                metadatas = [metadata] if isinstance(metadata, dict) else metadata
 
                 ids = [
                     hashlib.sha256(doc.encode("utf-8")).hexdigest() for doc in documents

src/crewai/llm.py

@@ -1,5 +1,4 @@
 import logging
-import os
 import sys
 import threading
 import warnings
@@ -129,7 +128,6 @@ class LLM:
         litellm.drop_params = True
         litellm.set_verbose = False
         self.set_callbacks(callbacks)
-        self.set_env_callbacks()
 
     def call(self, messages: List[Dict[str, str]], callbacks: List[Any] = []) -> str:
         with suppress_warnings():
@@ -204,39 +202,3 @@ class LLM:
                 litellm._async_success_callback.remove(callback)
 
         litellm.callbacks = callbacks
-
-    def set_env_callbacks(self):
-        """
-        Sets the success and failure callbacks for the LiteLLM library from environment variables.
-
-        This method reads the `LITELLM_SUCCESS_CALLBACKS` and `LITELLM_FAILURE_CALLBACKS`
-        environment variables, which should contain comma-separated lists of callback names.
-        It then assigns these lists to `litellm.success_callback` and `litellm.failure_callback`,
-        respectively.
-
-        If the environment variables are not set or are empty, the corresponding callback lists
-        will be set to empty lists.
-
-        Example:
-            LITELLM_SUCCESS_CALLBACKS="langfuse,langsmith"
-            LITELLM_FAILURE_CALLBACKS="langfuse"
-
-        This will set `litellm.success_callback` to ["langfuse", "langsmith"] and
-        `litellm.failure_callback` to ["langfuse"].
-        """
-        success_callbacks_str = os.environ.get("LITELLM_SUCCESS_CALLBACKS", "")
-        success_callbacks = []
-        if success_callbacks_str:
-            success_callbacks = [
-                callback.strip() for callback in success_callbacks_str.split(",")
-            ]
-
-        failure_callbacks_str = os.environ.get("LITELLM_FAILURE_CALLBACKS", "")
-        failure_callbacks = []
-        if failure_callbacks_str:
-            failure_callbacks = [
-                callback.strip() for callback in failure_callbacks_str.split(",")
-            ]
-
-        litellm.success_callback = success_callbacks
-        litellm.failure_callback = failure_callbacks

uv.lock

@@ -714,7 +714,7 @@ requires-dist = [
 [package.metadata.requires-dev]
 dev = [
     { name = "cairosvg", specifier = ">=2.7.1" },
-    { name = "crewai-tools", specifier = ">=0.14.0" },
+    { name = "crewai-tools", specifier = ">=0.17.0,<0.18.0" },
     { name = "mkdocs", specifier = ">=1.4.3" },
     { name = "mkdocs-material", specifier = ">=9.5.7" },
     { name = "mkdocs-material-extensions", specifier = ">=1.3.1" },